GOESB — Global Open Edge Speech Benchmark · pronounced “goose-bee”

Leaderboard

Objective, reproducible benchmarks for local (edge) speech AI. Every result here re-verified its hash and signature before being accepted — see why you can trust the numbers. New here? Read the docs.

This is every verified result, filterable and sortable. Looking for a single best recommendation for your constraints instead? Try the homepage →

Lowest energy Fastest (lowest RTF)Most accurate (lowest WER)

Benchmark typeLanguagePackRuntimeModelHardware

Clear

Quality gates:WER < 5%WER < 10%WER < 15%

custom…

No verified result yet for this exact combination.

Closest verified matches:

whisper-large-v3 / whisper-cpp · apple-m1-pro · nl-NL(pack)View
whisper-large-v3 / faster-whisper · apple-m1-pro · nl-NL(pack)View
whisper-medium / faster-whisper · apple-m1-pro · nl-NL(pack)View

Help fill this gap:

$ goesb run vosk-small-en-batch librispeech-en-vosk

Your result is signed locally and verified on submission. How submitting works → See what's most wanted →